TobiasLee/Chinese-Hip-pop-Generation

Generate Chinese hip-pop lyrics using GAN

46
/ 100
Emerging

Uses a modified SeqGAN architecture with TensorFlow and Jieba tokenization to condition lyric generation on input phrases while enforcing rhyme constraints via a lookup table. The model generates multi-line sequences by sampling from the generator network, with evaluation against ground-truth lyrics from a 10,000-sentence corpus. Includes utilities for single-line and paragraph-level generation with rhyme table integration.

131 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

131

Forks

30

Language

Python

License

MIT

Last pushed

Nov 19, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/TobiasLee/Chinese-Hip-pop-Generation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.